Discovering Prediction Rules in AHA! Courses

Abstract. In this paper we are going to show how to discover interesting prediction rules in student usage information, and use them to improve adaptive web courses. We have used AHA! to make a course that adapts both the presentation and the navigation depending on the level of knowledge that each particular student has. We have made several changes in AHA! to improve its power in the educational area. We use the logging information from AHA! to discover relations in the usage data (reading times, difficulty levels and test results). The most interesting relations are shown to the teacher so that he can carry out the appropriated modifications in the course to improve it.